Fusion of Multi-Spectral Information Using Invariant Algebra
Abstract
The very large varieties of the multi-sensor scene signatures that needs to be considered for building a robust machine-based scene analysis system requires that one explores the possibility of deriving multi-sensor representations that are at the least invariant to scale, translation, and rotation with respect to the observer. In this paper we develop methodologies for multi-sensor scene analysis based on the theory of invariant algebra. Two cases of similar and dissimilar sensor types are considered. The fused invariant for the case of similar sensor types are unchanged under material as well as under affine transformations. For the case of dissimilar sensors the approach leads to the derivation of the multi-sensor invariant expressions that remain unchanged under scale, translation and rotation with respect to the observer. Examples of the application of the approach on real multisensor data are presented.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1998
- Accession Number
- ADA399119
Entities
People
- Firooz Sadjadi
Organizations
- Lockheed Martin